def computeAreaDensity(zCoord, trainTags, focusPoints, testTimes):
"""
Takes in tags and compute densities for all the users
for the focus points specified
Note: This only needs to be run once per run, no need to do bayes opt
so maybe we can preprocess and store in file?
--
trainTags: list of user tags
focusPoints: list of focus points
[(a, b), (c, d), (e, f)] where a through f are floats
--
Returns: dict {timestamp: densityDistribution}
"""
print 'Generating test cases and computing shortest paths...'
dfFloor18 = generateTestCases(focusPoints, trainTags, level=zCoord)
dfFormattedFloor18 = formatDf(dfFloor18)
uniqueUserID = dfFormattedFloor18['USER'].unique()
dfFormattedFloor18['SHORTEST_PATHS'] = dfFormattedFloor18['SHORTEST_PATHS'].str.split(',')
result = pd.DataFrame()
#result = bayes.predictGP(dfFormattedFloor18[dfFormattedFloor18['USER'] == uniqueUserID[0]], testTimes)
densityDist = None
numOfSkippedFile = 0
# Iterate through each user
count = 0
for user in uniqueUserID:
print 'Computing GP', count, 'of', len(uniqueUserID), '. USER==', user
count += 1
userResult = bayes.predictGP(
dfFormattedFloor18[dfFormattedFloor18['USER'] == user],
testTimes)
userDensityDist = computeDensity(userResult, focusPoints, level=zCoord)
if densityDist is None:
densityDist = userDensityDist
else:
for timestamp in userDensityDist:
# All timestamps the same
# Add points
userDensityDistTimestamp = userDensityDist[timestamp]
densityDistTimestamp = densityDist[timestamp]
userDensityDistTimestampPoints = userDensityDistTimestamp.getPoints()
for point in userDensityDistTimestampPoints:
densityDistPoint = densityDistTimestamp.query(point)
if np.isnan(densityDistPoint):
print 'NAN DETECTED'
densityDistPoint = 0
addedProb = densityDistTimestamp.query(point) + userDensityDistTimestamp.query(point)
densityDist[timestamp].setPoint(point, addedProb)
return densityDist, numOfSkippedFile
def runBayes(df, testTimes):
"""
Takes in a dataframe of ['TIMESTAMP', 'USER', 'Z', SHORTEST_PATHS'] and
performs a GP regression and a GP prediction
---
df: dataframe output from formatDf method
['TIMESTAMP', 'USER', 'Z', SHORTEST_PATHS'] where
'SHORTEST_PATHS' is a series of 3-tuples, each of which contain shortest
distances of each of the 3 selected points
---
Returns:
A DataFrame of ['TIMESTAMP', 'MU', 'VAR'] for all users concatenated
'MU' and 'VAR' both contains series of 3-tuples
"""
print 'NOT BEING USED'
quit()
df['SHORTEST_PATHS'] = df['SHORTEST_PATHS'].str.split(',')
uniqueUserID = df['USER'].unique()
result = pd.DataFrame()
result = bayes.predictGP(df[df['USER'] == uniqueUserID[0]], testTimes)
'''
# Iterate through each user and regress then concat the output
for user in uniqueUserID:
userResult = bayes.predictGP(df[df['USER'] == user], testTimes)
result = pd.concat([result, userResult])
'''
return result
def runBayes(df, testTimes):
"""
Takes in a dataframe of ['TIMESTAMP', 'USER', 'Z', SHORTEST_PATHS'] and
performs a GP regression and a GP prediction
---
df: dataframe output from formatDf method
['TIMESTAMP', 'USER', 'Z', SHORTEST_PATHS'] where
'SHORTEST_PATHS' is a series of 3-tuples, each of which contain shortest
distances of each of the 3 selected points
---
Returns:
A DataFrame of ['TIMESTAMP', 'MU', 'VAR'] for all users concatenated
'MU' and 'VAR' both contains series of 3-tuples
"""
print 'NOT BEING USED'; quit()
df['SHORTEST_PATHS'] = df['SHORTEST_PATHS'].str.split(',')
uniqueUserID = df['USER'].unique()
result = pd.DataFrame()
result = bayes.predictGP(df[df['USER'] == uniqueUserID[0]], testTimes)
'''
# Iterate through each user and regress then concat the output
for user in uniqueUserID:
userResult = bayes.predictGP(df[df['USER'] == user], testTimes)
result = pd.concat([result, userResult])
'''
return result
def computeAreaDensity(zCoord, trainTags, focusPoints, testTimes):
"""
Takes in tags and compute densities for all the users
for the focus points specified
Note: This only needs to be run once per run, no need to do bayes opt
so maybe we can preprocess and store in file?
--
trainTags: list of user tags
focusPoints: list of focus points
[(a, b), (c, d), (e, f)] where a through f are floats
--
Returns: dict {timestamp: densityDistribution}
"""
print 'Generating test cases and computing shortest paths...'
dfFloor18 = generateTestCases(focusPoints, trainTags, level=zCoord)
dfFormattedFloor18 = formatDf(dfFloor18)
uniqueUserID = dfFormattedFloor18['USER'].unique()
dfFormattedFloor18['SHORTEST_PATHS'] = dfFormattedFloor18[
'SHORTEST_PATHS'].str.split(',')
result = pd.DataFrame()
#result = bayes.predictGP(dfFormattedFloor18[dfFormattedFloor18['USER'] == uniqueUserID[0]], testTimes)
densityDist = None
numOfSkippedFile = 0
# Iterate through each user
count = 0
for user in uniqueUserID:
print 'Computing GP', count, 'of', len(uniqueUserID), '. USER==', user
count += 1
userResult = bayes.predictGP(
dfFormattedFloor18[dfFormattedFloor18['USER'] == user], testTimes)
userDensityDist = computeDensity(userResult, focusPoints, level=zCoord)
if densityDist is None:
densityDist = userDensityDist
else:
for timestamp in userDensityDist:
# All timestamps the same
# Add points
userDensityDistTimestamp = userDensityDist[timestamp]
densityDistTimestamp = densityDist[timestamp]
userDensityDistTimestampPoints = userDensityDistTimestamp.getPoints(
)
for point in userDensityDistTimestampPoints:
densityDistPoint = densityDistTimestamp.query(point)
if np.isnan(densityDistPoint):
print 'NAN DETECTED'
densityDistPoint = 0
addedProb = densityDistTimestamp.query(
point) + userDensityDistTimestamp.query(point)
densityDist[timestamp].setPoint(point, addedProb)
return densityDist, numOfSkippedFile
